© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 532
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.72
    ]]:
    -0.66
     AssemblyCompany
    -0.66
    SourceChecksum
    -0.63
     lenker
    -0.62
     vœux
    -0.62
     efficaces
    -0.62
     positifs
    -0.62
    )}_
    -0.61
    лтемелер
    -0.58
    POSITIVE LOGITS
     from
    0.60
     transported
    0.56
     transferred
    0.55
     returned
    0.54
     Pristupljeno
    0.53
     then
    0.51
     delivered
    0.50
     brought
    0.50
     urine
    0.50
     released
    0.49
    Activations Density 0.005%

    No Known Activations